Spaces:
Sleeping
Sleeping
| ### 1. Imports and class names setup ### | |
| import gradio as gr | |
| import os | |
| import torch | |
| from model import create_effnetb2_model, create_vit_model | |
| from timeit import default_timer as timer | |
| from typing import Tuple, Dict | |
| # Setup class names | |
| class_names = ['cardboard', 'glass', 'metal', 'organic', 'paper', 'plastic', 'trash'] | |
| ### 2. Model and transforms preparation ### | |
| effnetb2, effnetb2_transforms = create_effnetb2_model( | |
| num_classes=len(class_names), | |
| ) | |
| vit, vit_transforms = create_vit_model( | |
| num_classes=len(class_names), | |
| ) | |
| # Load saved weights | |
| effnetb2.load_state_dict( | |
| torch.load( | |
| f="effnetb2_augmented_dataset_10_epochs.pth", | |
| map_location=torch.device("cpu") | |
| ) | |
| ) | |
| vit.load_state_dict( | |
| torch.load( | |
| f="vit_b_16_augmented_dataset_10_epochs.pth", | |
| map_location=torch.device("cpu") | |
| ) | |
| ) | |
| ### 3. Predict function ### | |
| def predict(img, model_str: str) -> Tuple[Dict, float]: | |
| # Start a timer | |
| start_time = timer() | |
| if model_str == "effnetb2": | |
| # Transform the image | |
| img = effnetb2_transforms(img).unsqueeze(0) | |
| model = effnetb2 | |
| model.eval() | |
| # Put model into eval mode, make prediction | |
| with torch.inference_mode(): | |
| # Pass transformed image through the model and turn the prediction logits into probabilities | |
| pred_probs = torch.softmax(model(img), dim=1) | |
| # Create a prediciton label and prediction probability dictionary | |
| pred_labels_and_probs = {class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))} | |
| # Calculate pred time | |
| pred_time = round(timer() - start_time, 4) | |
| # Return pred labels and pred time | |
| return pred_labels_and_probs, pred_time | |
| else: | |
| # Transform the image | |
| img = vit_transforms(img).unsqueeze(0) | |
| model = vit | |
| model.eval() | |
| # Put model into eval mode, make prediction | |
| with torch.inference_mode(): | |
| # Pass transformed image through the model and turn the prediction logits into probabilities | |
| pred_probs = torch.softmax(model(img), dim=1) | |
| # Create a prediciton label and prediction probability dictionary | |
| pred_labels_and_probs = {class_names[i]: float(pred_probs[0][i]) for i in range(len(class_names))} | |
| # Calculate pred time | |
| pred_time = round(timer() - start_time, 4) | |
| # Return pred labels and pred time | |
| return pred_labels_and_probs, pred_time | |
| ### 4. Gradio app - Gradio interface + launch command ### | |
| # Create title, description and article | |
| title = "Rubbish Classifier 🗑️" | |
| description = "An [EfficientNetb2 feature extractor](https://pytorch.org/vision/stable/models/generated/torchvision.models.efficientnet_b2.html#torchvision.models.efficientnet_b2) and a [ViT feature extractor](https://pytorch.org/vision/stable/models/generated/torchvision.models.vit_b_16.html#torchvision.models.vit_b_16) model to classify rubbish images." | |
| article = "Created by me" | |
| # Create example list | |
| example_list = [["examples/" + example] for example in os.listdir("examples")] | |
| # Create the Gradio demo | |
| demo = gr.Interface(fn=predict, | |
| inputs=[gr.Image(type="pil"), | |
| gr.Dropdown(choices=['effnetb2', 'vit'], label='Model To Use', value='effnetb2')], | |
| outputs=[gr.Label(num_top_classes=3, label="Predictions"), | |
| gr.Number(label="Prediction time (s)")], | |
| examples=example_list, | |
| title=title, | |
| description=description, | |
| article=article) | |
| # Launch the demo | |
| demo.launch(debug=False, share=True) | |